© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 5499
    Prev
    Next
    INDEX
    Explanations

    references to social media platforms and interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "Twitter" or tweets

    np_acts-logits-general · gemini-2.0-flash

    twitter and tweets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    makeConstraints
    -0.68
     Portail
    -0.62
    modelBuilder
    -0.62
     ostavi
    -0.61
    Begriffsklä
    -0.58
    Hauptartikel
    -0.58
     Koz
    -0.57
    таратура
    -0.55
     Chalmers
    -0.54
    ỡng
    -0.54
    POSITIVE LOGITS
     tweets
    1.44
     tweeting
    1.33
     tweet
    1.32
     Twitter
    1.31
     Tweets
    1.27
     tweeted
    1.26
    Twitter
    1.23
     twitter
    1.22
    twitter
    1.18
    TWITTER
    1.16
    Activations Density 0.061%

    No Known Activations